Fotis Drakopoulos

Hello all, I'm also trying to setup the openMHA with a Raspberry Pi 3+ and a Cirrus Logic audio card and I am having the same problem. During boot I...

Hi Marc, Thanks for the prompt reply! I was hoping to test the openMHA prototype at first so I don't have the complete setup (I am using a headset without...

Hi Marc, Thanks a lot for your help. I set up the openMHA after all from your SD-card image by bypassing your static feedback algorithm, I'm now trying to find...

The previous implementation was incorrect. I've written an example implementation of how the Categorical mean should be, the code below works for me and produces the desired result. The mean...

> I don't think there is currently an implementation. The following might be simpler: tf.reduce_sum(tf.range(self._num_categories(probs)) * probs, axis=-1) / tf.reduce_sum(probs, axis=-1) You could send a PR, sure. Hi, Indeed this...

> As a first step, I've created an example script based on your script above, see #10. > > Any suggestions for improvements? Great, the example seems pretty good! I...

> But now that I'm thinking about it ... probably it wouldn't hurt to add a delay of `dsp_size` frames? > Anyway, I think it doesn't really matter, because pre-filling...

> This is strange. How are you measuring the duration? I'm just measuring using time.time(): ``` t=time() clean = processing_algorithm(noisy) print(time()-t) ``` > Yeah, this looks like a bug somewhere....

> I have no idea yet what could be going wrong there. Probably it's just a silly bug in the callback function. How can I reproduce the problem? That's the...

> If you can strip it down far enough, I'd like to have a look. But I don't want to spend too much time installing a bunch of complicated libraries,...